MMClassification Release V0.16.0

Highlights

• We have improved compatibility with downstream repositories like MMDetection and MMSegmentation. We will add some examples about how to use our backbones in MMDetection.
• Add RepVGG backbone and checkpoints. Welcome to use it!
• Add timm backbones wrapper, now you can simply use backbones of pytorch-image-models in MMClassification!

New Features

• Add RepVGG backbone and checkpoints. (#414)
• Add timm backbones wrapper. (#427)

Improvements

• Fix TnT compatibility and verbose warning. (#436)
• Support setting --out-items in tools/test.py. (#437)
• Add datetime info and saving model using torch<1.6 format. (#439)
• Improve downstream repositories compatibility. (#421)
• Rename the option --options to --cfg-options in some tools. (#425)
• Add PyTorch 1.9 and Python 3.9 build workflow, and remove some CI. (#422)

Bug Fixes

• Fix format error in test.py when metric returns np.ndarray. (#441)
• Fix publish_model bug if no parent of out_file. (#463)
• Fix num_classes bug in pytorch2onnx.py. (#458)
• Fix missing runtime requirement packaging. (#459)
• Fix saving simplified model bug in ONNX export tool. (#438)

Docs Update

• Update getting_started.md and install.md. And rewrite finetune.md. (#466)
• Use PyTorch style docs theme. (#457)
• Update metafile and Readme. (#435)
• Add CITATION.cff. (#428)

Contributors

A total of 8 developers contributed to this release.
@Charlyo @Ezra-Yu @mzr1996 @amirassov @RangiLyu @zhaoxin111 @uniyushu @zhangrui-wolf